NCBR-227

Data

Kaplan-Meier Analysis

Mixed Effect Cox Regression

Cox proportional hazard model is commonly used in survival analysis that models the hazard function which denotes the instantaneous rate of the occurrence of an event at a time given that the subject survived upto that point. Including random effect in the Cox’s proportional hazard model enables us to incorporate within group homogeneity in outcomes. A mixed effect model in general multivariate analysis is used to control for relatedness in the samples. I used the kinship matrix (kinship2 R package) to correct for relatedness as a random effect.

	Surv(ageonset, censor)
Predictors	HR	CI	p
mutation Class [C term]	1.79	0.53 – 6.05	0.346
mutation Class [Null]	3.36	1.67 – 6.77	0.001
mutation Class [Truncation]	5.70	2.42 – 13.42	<0.001
Gender [2]	1.06	0.58 – 1.92	0.852
N _Indiv.ID	128
Observations	128

Enhancer is selected as the baseline mutation class. All the mutation other than C-term increases risk compared to enhancer mutation. An individual with truncation mutation has five times hazard than an individual with enhancer mutation. To be able to compare each mutation class, I used emmeans package. Note that, results in the following table are averaged over the levels of: Gender. P value adjustment was made using tukey method for comparing a family of 5 estimates.

Most important assumption for this model is the “proportional hazard” which was not violated.

               chisq df    p
mutation.Class  4.65  3 0.20
Gender          0.87  1 0.35
GLOBAL          4.86  4 0.30

Sample size for testing difference between missense group is 81. R398 is selected as the baseline missense group. Missense group R396 (strong evidence p < 0.01) and T354 (moderate evidence p< 0.05) increases risk compared to R398 missense mutation. An individual with R396 missense mutation on an average has two and half times higher hazard than an individual with R398 mutation.

	Surv(ageonset, censor)
Predictors	HR	CI	p
Missense group [R361]	1.63	0.79 – 3.35	0.186
Missense group [R396]	2.67	1.36 – 5.26	0.004
Missense group [T354]	2.16	1.09 – 4.31	0.028
Gender [2]	1.17	0.69 – 1.99	0.549
N _Indiv.ID	81
Observations	81

Packages and Citations

R version 4.2.2 (2022-10-31)
Platform: x86_64-apple-darwin17.0 (64-bit)
Running under: macOS Big Sur ... 10.16

Matrix products: default
BLAS:   /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRlapack.dylib

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] kableExtra_1.3.4 kinship2_1.9.6   quadprog_1.5-8   Matrix_1.5-1    
 [5] xtable_1.8-4     coxme_2.2-18.1   bdsmatrix_1.3-6  survminer_0.4.9 
 [9] ggpubr_0.5.0     DT_0.27          forcats_1.0.0    stringr_1.5.0   
[13] dplyr_1.1.0      purrr_1.0.1      readr_2.1.3      tidyr_1.3.0     
[17] tibble_3.1.8     ggplot2_3.4.0    tidyverse_1.3.2  survival_3.4-0  
[21] readxl_1.4.1    

loaded via a namespace (and not attached):
  [1] minqa_1.2.5          googledrive_2.0.0    colorspace_2.1-0    
  [4] ggsignif_0.6.4       ellipsis_0.3.2       sjlabelled_1.2.0    
  [7] estimability_1.4.1   markdown_1.5         parameters_0.20.2   
 [10] fs_1.6.1             gridtext_0.1.5       ggtext_0.1.2        
 [13] rstudioapi_0.14      farver_2.1.1         mvtnorm_1.1-3       
 [16] fansi_1.0.4          lubridate_1.9.1      xml2_1.3.3          
 [19] splines_4.2.2        cachem_1.0.6         knitr_1.42          
 [22] sjmisc_2.8.9         jsonlite_1.8.4       nloptr_2.0.3        
 [25] ggeffects_1.1.5      broom_1.0.3          km.ci_0.5-6         
 [28] dbplyr_2.3.0         effectsize_0.8.3     compiler_4.2.2      
 [31] httr_1.4.4           sjstats_0.18.2       emmeans_1.8.4-1     
 [34] backports_1.4.1      assertthat_0.2.1     fastmap_1.1.0       
 [37] gargle_1.3.0         cli_3.6.0            htmltools_0.5.4     
 [40] tools_4.2.2          coda_0.19-4          gtable_0.3.1        
 [43] glue_1.6.2           Rcpp_1.0.10          carData_3.0-5       
 [46] cellranger_1.1.0     jquerylib_0.1.4      vctrs_0.5.2         
 [49] sjPlot_2.8.12        svglite_2.1.1        nlme_3.1-160        
 [52] crosstalk_1.2.0.9000 insight_0.19.0       xfun_0.37           
 [55] lme4_1.1-31          rvest_1.0.3          timechange_0.2.0    
 [58] lifecycle_1.0.3      rstatix_0.7.2        googlesheets4_1.0.1 
 [61] MASS_7.3-58.1        zoo_1.8-11           scales_1.2.1        
 [64] hms_1.1.2            yaml_2.3.7           gridExtra_2.3       
 [67] KMsurv_0.1-5         sass_0.4.5           stringi_1.7.12      
 [70] bayestestR_0.13.0    boot_1.3-28          rlang_1.0.6         
 [73] pkgconfig_2.0.3      systemfonts_1.0.4    commonmark_1.8.1    
 [76] evaluate_0.20        lattice_0.20-45      htmlwidgets_1.6.1   
 [79] labeling_0.4.2       tidyselect_1.2.0     magrittr_2.0.3      
 [82] R6_2.5.1             generics_0.1.3       DBI_1.1.3           
 [85] pillar_1.8.1         haven_2.5.1          withr_2.5.0         
 [88] datawizard_0.6.5     abind_1.4-5          performance_0.10.2  
 [91] modelr_0.1.10        crayon_1.5.2         car_3.1-1           
 [94] survMisc_0.5.6       utf8_1.2.3           tzdb_0.3.0          
 [97] rmarkdown_2.20       grid_4.2.2           data.table_1.14.6   
[100] reprex_2.0.2         digest_0.6.31        webshot_0.5.4       
[103] munsell_0.5.0        viridisLite_0.4.1    bslib_0.4.2

Citation for R itself

[1] "R Core Team (2022). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/."

Citation for survival package


To cite package 'survival' in publications use:

  Therneau T (2022). _A Package for Survival Analysis in R_. R package
  version 3.4-0, <https://CRAN.R-project.org/package=survival>.

  Terry M. Therneau, Patricia M. Grambsch (2000). _Modeling Survival
  Data: Extending the Cox Model_. Springer, New York. ISBN
  0-387-98784-3.

To see these entries in BibTeX format, use 'print(<citation>,
bibtex=TRUE)', 'toBibtex(.)', or set
'options(citation.bibtex.max=999)'.

Citation for coxme


To cite package 'coxme' in publications use:

  Therneau TM (2022). _coxme: Mixed Effects Cox Models_. R package
  version 2.2-18.1, <https://CRAN.R-project.org/package=coxme>.

A BibTeX entry for LaTeX users is

  @Manual{,
    title = {coxme: Mixed Effects Cox Models},
    author = {Terry M. Therneau},
    year = {2022},
    note = {R package version 2.2-18.1},
    url = {https://CRAN.R-project.org/package=coxme},
  }

Citation for kinship2


To cite package 'kinship2' in publications use:

  Sinnwell J, Therneau T (2022). _kinship2: Pedigree Functions_. R
  package version 1.9.6, <https://CRAN.R-project.org/package=kinship2>.

A BibTeX entry for LaTeX users is

  @Manual{,
    title = {kinship2: Pedigree Functions},
    author = {Jason Sinnwell and Terry Therneau},
    year = {2022},
    note = {R package version 1.9.6},
    url = {https://CRAN.R-project.org/package=kinship2},
  }